一句话：探索用 GPT-3.5 等大语言模型充当渗透测试的“AI 陪练”，实现高层任务规划与虚拟机内低层漏洞挖掘。
渗透测试高度依赖专家经验，包含大量手工测试与分析步骤。本文探讨将 GPT-3.5 等大语言模型用作渗透测试者的“AI 陪练”，并考察了两个不同场景：一是面向安全测试任务的高层任务规划，二是针对存在漏洞的虚拟机内部的低层漏洞搜寻。在后者中，作者构建了一个闭环反馈系统：由 LLM 生成低层操作动作，通过 SSH 在虚拟机中自动执行，再把机器状态回馈给模型，使其分析潜在漏洞并给出具体攻击向量，随后自动执行这些攻击。论文报告了初步但有希望的结果，讨论了改进方向，并最后就 AI 陪练的伦理问题进行思辨。评估以案例式的探索性实验为主，尚未进行系统性量化评测。
The field of software security testing, more specifically penetration testing, requires high levels of expertise and involves many manual testing and analysis steps. This paper explores the potential use of large-language models, such as GPT3.5, to augment penetration testers with AI sparring partners. We explore two distinct use cases: high-level task planning for security testing assignments and low-level vulnerability hunting within a vulnerable virtual machine. For the latter, we implemented a closed-feedback loop between LLM-generated low-level actions with a vulnerable virtual machine (connected through SSH) and allowed the LLM to analyze the machine state for vulnerabilities and suggest concrete attack vectors which were automatically executed within the virtual machine. We discuss promising initial results, detail avenues for improvement, and close deliberating on the ethics of AI sparring partners.